from __future__ import generators
#-------------------------------------------------------------------------------
#
# Convert an HTML file generated by Microsoft Word into one or more HTML files.
#
# It includes the ability to:
# - Create an external CSS style sheet used by all generated pages.
# - Automatically insert default or custom navigation links at the top and
# bottom of each page.
# - Generate Microsoft Help Compiler compatible .hhc (table of contents),
# .hhp (project), .stp (stop word list) and .chm (compiled help module)
# files.
#
# Written by: David C. Morrill
#
# Date: 07/07/2003
#
# (c) Copyright 2003 by David C. Morrill
#
#-------------------------------------------------------------------------------
#
# To Do:
# - Allow option to define your own document template to replace the default
# tags.
# - Allow option to use page titles as file names.
# - Allow defining a custom, external document body processing function.
# - Allow defining a custom external function that receives all page titles
# and URL's, for generating custom navigation aids. This option could be
# used to:
# - Generate a table of contents page.
# - Generate Javascript pop-up navigation menu.
# (Maybe the previous two items should be combined into a single external
# class with optional methods that can be invoked, like a delegate. The
# option should allow multiple delegates).
# - 'YakBack' related items:
# - Allow e-mail to be sent on each new post.
# - Allow priviledged user(s) to delete comments.
# - Allow suppressing sections with no comments on log page.
# - Worry about file locking during updates?
# - Issues on non-IE browsers:
# - Mozilla under Red Hat: Click in 'Show tags' mode locks it in 'off'
# mode instead on 'on' mode. Links are underlined in blue.
# - Mac OS X Safari: 'Save preferences' link only runs 'false' script.
#
#-------------------------------------------------------------------------------
#-------------------------------------------------------------------------------
# Imports:
#-------------------------------------------------------------------------------
import sys
import re
import os.path
import binascii
from getopt import getopt, GetoptError
from exceptions import ValueError
from os import system
from time import time, asctime
#-------------------------------------------------------------------------------
# Constants:
#-------------------------------------------------------------------------------
# Last heading level processed:
LAST_HEADING = 9
# Special CSS styles:
special_styles = [ 'a:link', 'a:visited', 'a:active', 'a:hover' ]
# Ignore CSS styles:
ignore_styles = [ '@page' ]
# Standard HTML file extensions:
html_exts = [ '.html', '.htm' ]
# Parsing regular expressions:
tag_pat = re.compile( r'<(.*?)>| |\r',
re.DOTALL | re.IGNORECASE )
title_pat = re.compile( r'(.*?)',
re.DOTALL | re.IGNORECASE )
style_pat = re.compile( r'',
re.DOTALL | re.IGNORECASE )
body_pat = re.compile( r']*?)>(.*)',
re.DOTALL | re.IGNORECASE )
comment_pat = re.compile( r'/\*(.*?)\*/',
re.DOTALL | re.IGNORECASE )
fontface_pat = re.compile(
r'\s@font-face\s+?{\s*?font-family:\s*?"?(.*?)"?;(.*?)}',
re.DOTALL | re.IGNORECASE )
fontfamily_pat = re.compile( r'''font-family\s*:\s*['"]?([a-zA-Z0-9 ]*)''',
re.DOTALL | re.IGNORECASE )
class_pat = re.compile( r'\sclass=([a-zA-Z0-9_]*)\s',
re.DOTALL | re.IGNORECASE )
instyle_pat = re.compile( r'''\sstyle=(['"])(.*?)\1''',
re.DOTALL | re.IGNORECASE )
ahref_pat = re.compile( r'